10 ай бұрын
Пікірлер
@meruem6995ujjoooo 2 күн бұрын
Agreed
@hannespeter1484 5 күн бұрын
Would you think that can be applied for generative protein structure decoders aswell?
@Pingu_astrocat21 5 күн бұрын
Super cool work😁
@patrickjiang402 6 күн бұрын
Wonderful talk! Thank you so much for sharing again!
@nelsonndahiro6115 6 күн бұрын
2 videos in a day, must be an early Christmas 😍😍
@naromsky 6 күн бұрын
Sorry, but what a terrible talk.
@raoufkeskes7965 10 күн бұрын
can we get the presentation in a pdf format please ?
@mlforproteinengineeringsem6420 10 күн бұрын
unfortunately, we do not get slides from our speakers, sorry for any disappointment.
@tanutchajenpanitcheep3723 Ай бұрын
BdbHr mm HC mm is
@GrayDelia 3 ай бұрын
805 Hallie Cliffs
@roberthill5373 6 ай бұрын
They just updated their arXiv paper in May 6, 2024, and still not show code repo in github. Will be time-consumed if we want to work bottom up, and may not be worthing it if it is not any better than RFDiffusion All-Atom.
@obsoletepowercorrupts 7 ай бұрын
This could be used for Ribosomopathies _(abnormalities in rRNA genes, ribosomal component proteins)_ in anaemia and bone marrow, to pre-emptively reverse engineer them by computer. So one makes a new, custom, ribosome organelle computationally. Comparison across genus and species could be for hypothetical empirical emulation _(and as an aside, sexual selection for immune system traits could be postulated, for inbreeding and outbreeding or phenotype)._ Cancer susceptibility and mitigating factors such as premature cell death _(not solely mutation from RNA interference)_ could be predicted. Extension to sickle cell prediction would be a worthwhile investigation. For instance: Narrow down and isolate the Mutation Preference Inference from RNA interference by means of singular value decomposition used in _(including Gaussian)_ noise elimination with a logistics fit, also by linear regression and derive if it is in a sparse matrix or dense matrix. Express the molecular Schrödinger electron density _(Gaussian probability estimation, in a Rosenblatt-Parzen window treating the kernel as its hypercube)_ as kissing-spheres _(or sphere packing via combinatorial optimisation)._ For learning _(educationally but also for machine-learning),_ that could be done in R (cran-project) for better graphics fo the polynomials but other than that, python would be similar enough language. OpenCL for heterogeneous low power computation _(low power implant medical devices for instance)_ might be an option although DLib and Eigen maths libraries for C++ would augment it. As an (extra) aside, discovery of the mechanisms of diploidisation in the (sans meiosis) parasexual cycle _(fungi and prokaryote, in mitosis)_ could be researched using singular value decomposition for theoretical soil emulation and fungi creation (or a plant) for antibiotic discovery. Then apply that to neofunctionalisation, subfunctionalisation and genome downsizing (post-polyploidisation diploidisation), for instance, as relevant to DNA repetition and gene deletion _(and extraneous gene copies with alleles in Eukaryota's taxonomic groups)._ My comment has no hate in it and I do no harm. I am not appalled or afraid, boasting or envying or complaining... Just saying. Psalms23: Giving thanks and praise to the Lord and peace and love. Also, I'd say Matthew6.
@davidedavidedav 8 ай бұрын
Nice, and what about GO terms prediction?
@nelsonndahiro5220 8 ай бұрын
"Unreasonable usefulness of self-supervised" is right. It's actually weird that simply a higher likelihood per AA is enough to improve various proteins
@Skar1ath 9 ай бұрын
Please make a video on how it is actually runs.
@wubishetmengistu5874 10 ай бұрын
Literally audio plus of the article and science ! Beautiful and superb.
@ConnorLewis-i2m 11 ай бұрын
As cutting edge as it gets. Amazing work. Very cool to hear about how by essentially solving an engineering problem and evolving PACE to PRANCE, Erika is more readily able to understand how and why the final protein variants are evolved. I read Kevin Esvelt's PACE paper in my first or second year of grad school and have been following the developments in this area ever since and it never fails to inspire me. The synthetic phylogenies that the PRANCE system can help generate will surely provide some incredible insights.
@castilloh.gianmarco1048 11 ай бұрын
niceee! <3
@waylon2432 Жыл бұрын
Promo-SM 😒
@crispisauce Жыл бұрын
don't care if no code. They probably just re-trained RFDiffuser anyway...
@EdT.-xt6yv Жыл бұрын
4:00 active site , enzyme? 9:15 bacterial phosphate 12:18 transition state , analog 14:40 TUNGSTATE 22:15 enzyme works
@mahmoudebrahimkhani1384 Жыл бұрын
I could not find any GitHub repository cited in the arXiv paper. Do you know if the model and code are available?
@mahmoudebrahimkhani1384 Жыл бұрын
Congratulations on this very nice piece of work!
@EdT.-xt6yv Жыл бұрын
13:00 noise2DATA
@EdT.-xt6yv Жыл бұрын
11:00
@ChuengEfranc Жыл бұрын
I want to know what's the best tool for homomer structure prediction now, is it still af2-multimer？
@HungNguyen-lp8ql Жыл бұрын
No code?
@lo8885 Жыл бұрын
In your opinion the viewers : In what sense would it be interesting to train EvoDiff-seq (without modifying its architecture) on the PDB dataset of 200K sequences, these sequences that have been used to train RFDiffusion and the state of the art structure based generative models.
@jakeparker1287 Жыл бұрын
Not very. The whole point is to leverage the huge sequence-only datasets available, of which the pdb is a very small subset.
@trevy5273 Жыл бұрын
Many thanks for this summery, very helpful!
@PhiLordGenetic Жыл бұрын
im using the google colab platform that they put on github but i don't know exactly the configurations, imt trying to creat a binder
@Willpower1265 Жыл бұрын
You guys are my heroes, congratulations! Nobel prize perhaps?
@etashbhat6128 Ай бұрын
Predicted it a year in advance!
@tohidialireza7236 Жыл бұрын
hi Where can I find the presentation slides?
@yaoyu4798 Жыл бұрын
38:23 this is amazing work! I am very new to this. A naive question, for the last example, what info do you need to provide to the model to get the binder? Do you provide any guidance in terms of backbone info or any other minimal info?
@PhiLordGenetic Жыл бұрын
did you get any answer?
@yaoyu4798 Жыл бұрын
@@PhiLordGenetic nope haha
@Fouriersoft Жыл бұрын
Very nice -- does anyone know what the 'rep 1.2' means in her sampling method? I'm guessing 950 tokens with the highest probability were sampled 'randomly' (multinomially) and the rest were omitted? What does the 'rep 1.2' mean here?
@neseruzgari Жыл бұрын
A question: if I want to design 10000 sequences with ProteinMPNN, is it better to use one seed for all, or one seed per sequence to increase diversity? what do you think?
@fatmadoll 5 ай бұрын
I have been wondering the same thing, especially since I parallelize my process. Any idea what's the best way to do this?
@secretsoul6882 Жыл бұрын
Interesting and wonderful presentation, very clear! Thanks for sharing knowledge.
@sabaokangan Жыл бұрын
Thank you so much for sharing this with us on KZbin
@waldenli9232 Жыл бұрын
Great work. Very helpful to the community to encompass these exciting new evolutionary methods and combine with learning from the assay labeled data (so that we don't have to re-live the ordeal that you went through). Thanks also for sharing the person behind the work. The picture of one researcher looking at a big sea around them probably resonates with many. People can be more at ease after hearing about what it was like for you :)
@giovannimazzocco4999 Жыл бұрын
Interesting talk. Do you think this method could be extended to predict peptide-protein or protein-protein interactions? If that's not the case could you explain what are the main limitations in going in that direction?
@allanqiao Жыл бұрын
that could need more hashrate and may expenstive
@马鹏森 Жыл бұрын
A good paper, but I think it would have been better if the author had been more flow-through, rather than using "uh" all the time.
@EdT.-xt6yv 10 ай бұрын
1.5x speed
@wichetleelamanit6195 Жыл бұрын
Thank you for sharing the knowledge.
@hippofri Жыл бұрын
Great talk, thanks for recording and putting this up!
@ShanilPanara Жыл бұрын
One of the best talks I've heard in a while, super clear presentation, and super interesting research! Thanks Emily ☺️
@bojeingwersen1082 Жыл бұрын
can't wait to try it out!
@javadlotfi508 Жыл бұрын
impressive !!! appreciate the hard work
@seanpeldomzhang8844 Жыл бұрын
This work is unprecedented!
@sabaokangan Жыл бұрын
Thank you so much for sharing this with us on KZbin
@Poppik81 Жыл бұрын
Cool stuff, thank you. I wonder how to plug in a sequence that is not from MSA, not knowing where are gaps.
@ginaelnesr Жыл бұрын
For the calculations to all work out and to be able to project the new sequence into space, the new sequence should have the same length as the sequences in the MSA. There are some tricks you can do depending on whether or not the new sequence is longer or shorter than the MSA length to “change” the sequence length… and that is definitely case-dependent.
@sabaokangan Жыл бұрын
Thank you so much for sharing this with us!
@sabaokangan Жыл бұрын
Thank you so much for sharing this with us ❤🔥 from Seoul NationalU🇰🇷
@jiayili123 Жыл бұрын
this topic and article was published in nature communications